SOURCE-LINKED INTELLIGENCE

Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

Apple Machine Learning Research · article · Sep 24, 2026 · UTC

System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the language model reads. Because that model is sparsely activated under Instruction-Following Pruning, only a small subset of its experts occupies DRAM at any time, so the always-on tokenizer competes for the same memory, and its parameter count bears directly on power and latency. In this work we study how to compress such a tokenizer by distillation, taking as the supervision…

Read original source ↗ Open in workspace

recordType

article

region

Global